【摘要】 任务型对话系统中的自然语言生成模块(ToDNLG)旨在将系统的对话动作转换为自然语言回复，其受到研究者的广泛关注。随着深度神经网络的发展和预训练语言模型的爆发，ToDNLG的研究已经获得了重大突破。然而，目前仍然缺乏对现有方法和最新趋势的全面调研。为了填补这个空白，该文全面调研了ToDNLG的最新进展和前沿领域，包括：(1)系统性回顾：回顾和总结了ToDNLG近10年的发展脉络和方法，包括非神经网络时代和基于深度学习的ToDNLG工作；(2)前沿与挑战：总结了复杂ToDNLG等一些新兴领域及其相应的挑战；(3)丰富的开源资源：该文在一个公共网站上收集、整理了相关的论文、基线代码和排行榜，供ToDNLG的研究人员直接了解最新进展，希望该文的调研工作能够促进ToDNLG领域的研究工作。更多还原

【Abstract】 Natural Language Generation in a task-oriented dialogue system(ToDNLG) aims to generate natural language responses given the corresponding dialogue acts, which has attracted increasing research interest. With the development of deep neural networks and pre-trained language models, great success has been witnessed in the research of ToDNLG field. We present a comprehensive survey of the research field, including:(1) a systematical review on the development of NLG in the past decade, covering the traditional methods and deep learning-based methods;(2) new frontiers in emerging areas of complex ToDNLG as well as the corresponding challenges;(3) rich open-source resources, including the related papers, baseline codes and the leaderboards on a public website. We hope the survey can promote future research in ToDNLG.更多还原